© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 55387
    Prev
    Next
    INDEX
    Explanations

    instances of the word "transform" or its variations, indicating a focus on change or alteration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IMS
    -0.07
    ensa
    -0.07
    bung
    -0.07
     lamp
    -0.07
    onnement
    -0.07
    νοÏį
    -0.06
    clair
    -0.06
    bolt
    -0.06
    bage
    -0.06
    elp
    -0.06
    POSITIVE LOGITS
    ative
    0.07
    ations
    0.07
    zel
    0.06
     Vill
    0.06
    avia
    0.06
    esser
    0.06
     Zy
    0.06
    914
    0.06
     decltype
    0.06
    ATIONS
    0.06
    Activations Density 0.003%

    No Known Activations